How to Use the Formilla MCP in LangChain

Chain Formilla live chat data directly into your LangChain workflows to update contacts and pull visitor logs on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Formilla MCP to LangChain

Create your Vinkius account to connect Formilla to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Formilla with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync live chat data inside LangChain runs

Your LangChain agents can now look up who is chatting on your site without you writing custom API glue. By calling `get_contact_by_email` or `get_conversation`, your agent inspects active chats, pulls down visitor logs, and figures out who needs immediate human help. The output of these tools feeds straight into the next step of your chain. When a chat ends, the agent uses `upsert_contact` to update the user's record with notes from the conversation, keeping your CRM updated in real-time.

Run multi-step support triage pipelines

Stop writing hardcoded routing rules. You can build a LangGraph pipeline that uses `list_conversations` to grab active threads, then passes each thread to a classifier step to identify high-value leads. If the lead is qualified, the chain automatically runs `update_contact` to tag them or triggers `list_segments` to see where they fit. You get full observability through LangSmith, tracking every single tool call and token spent.

Keep your support database clean using MCP Server tools

Duplicate contact records are a massive headache. This MCP Server lets your agent run `search_contacts` to check if a visitor already exists before creating a new entry. If the email matches, the agent updates the existing profile using `update_contact`. If it's a spam bot, the agent can call `delete_contact` to purge the record instantly, keeping your database clean.

Setup guide

Set up Formilla MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Formilla tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "formilla-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Formilla transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Formilla. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Formilla now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Formilla MCP in LangChain

You use the MultiServerMCPClient to connect to the MCP server endpoint, then call get_tools(). This returns a list of tools like get_conversation that you pass directly into your agent's constructor.

Yes, if you use LangSmith tracing. Every time your agent calls list_contacts or upsert_contact, LangSmith logs the input parameters, execution latency, and exact token count.

The server runs in a secure Vinkius sandbox, but you should handle retries in your LangChain runnable chains. If list_conversations hits a limit, your chain can catch the error and back off.

Yes, you can run a local test easily. Just configure your environment variables with your API key, spin up the server, and point your LangChain setup to the Vinkius endpoint.

Your chat logs, visitor emails, and contact records are fully isolated. Vinkius runs this server in an ephemeral V8 sandbox, meaning no chat history or contact details are ever written to persistent disk or shared between sessions.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript